Xiangbo Shu

vision-language model (3) video understanding (3) noisy label (3) representation learning (2) domain adaptation (2) zero-shot learning (2) robust learning (2) action recognition (2) face aging (2) contrastive learning (2) federated learning (2) image classification (2) object detection (1) change detection (1) uncertainty modeling (1) catastrophic forgetting (1) domain generalization (1) token learning (1) probabilistic modeling (1) self-supervised learning (1)